{"title":"基于人工智能的高耐受糠醛和生产丁醇梭菌的筛选","authors":"","doi":"10.1016/j.bej.2024.109435","DOIUrl":null,"url":null,"abstract":"<div><p>Advances in strain breeding for butanol biosynthesis were quite limited because of physiological complexity of solventogenic <em>Clostridia</em>. Using AI, this study developed a high-throughput screening method for <em>Clostridium acetobutylicum</em> to find strains with inhibitor tolerance and high butanol production. A mutant library was generated from <em>C. acetobutylicum</em> ATCC 824 through ARTP mutagenesis and physiological traits were digitized using color indicators. The classification performance of Machine learning algorithms (PCA, PLS, SVM, ANN) were compared for different butanol-producing strains. Among 2000 strains screened, <em>C. acetobutylicum</em> Tust-f3 was identified, which could tolerate 4.5 g/L furfural and yield 10.5 g/L butanol from undetoxified lignocellulosic hydrolysate. Proteome analysis reveals that 38 proteins may play a crucial role. Subsequently, seven universal detoxification components for furfural were identified via heterologous expression in <em>E. coli</em> Genes CA_RS19590 and CA_RS08810 showed significant growth improvement (14.44 and 14.28-fold, respectively, compared to control). This study highlights the potential of machine learning in strain selection and breeding.</p></div>","PeriodicalId":8766,"journal":{"name":"Biochemical Engineering Journal","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AI-based screening of Clostridium acetobutylicum with high furfural tolerance and butanol production\",\"authors\":\"\",\"doi\":\"10.1016/j.bej.2024.109435\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Advances in strain breeding for butanol biosynthesis were quite limited because of physiological complexity of solventogenic <em>Clostridia</em>. Using AI, this study developed a high-throughput screening method for <em>Clostridium acetobutylicum</em> to find strains with inhibitor tolerance and high butanol production. A mutant library was generated from <em>C. acetobutylicum</em> ATCC 824 through ARTP mutagenesis and physiological traits were digitized using color indicators. The classification performance of Machine learning algorithms (PCA, PLS, SVM, ANN) were compared for different butanol-producing strains. Among 2000 strains screened, <em>C. acetobutylicum</em> Tust-f3 was identified, which could tolerate 4.5 g/L furfural and yield 10.5 g/L butanol from undetoxified lignocellulosic hydrolysate. Proteome analysis reveals that 38 proteins may play a crucial role. Subsequently, seven universal detoxification components for furfural were identified via heterologous expression in <em>E. coli</em> Genes CA_RS19590 and CA_RS08810 showed significant growth improvement (14.44 and 14.28-fold, respectively, compared to control). This study highlights the potential of machine learning in strain selection and breeding.</p></div>\",\"PeriodicalId\":8766,\"journal\":{\"name\":\"Biochemical Engineering Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2024-07-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biochemical Engineering Journal\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1369703X24002225\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biochemical Engineering Journal","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1369703X24002225","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
AI-based screening of Clostridium acetobutylicum with high furfural tolerance and butanol production
Advances in strain breeding for butanol biosynthesis were quite limited because of physiological complexity of solventogenic Clostridia. Using AI, this study developed a high-throughput screening method for Clostridium acetobutylicum to find strains with inhibitor tolerance and high butanol production. A mutant library was generated from C. acetobutylicum ATCC 824 through ARTP mutagenesis and physiological traits were digitized using color indicators. The classification performance of Machine learning algorithms (PCA, PLS, SVM, ANN) were compared for different butanol-producing strains. Among 2000 strains screened, C. acetobutylicum Tust-f3 was identified, which could tolerate 4.5 g/L furfural and yield 10.5 g/L butanol from undetoxified lignocellulosic hydrolysate. Proteome analysis reveals that 38 proteins may play a crucial role. Subsequently, seven universal detoxification components for furfural were identified via heterologous expression in E. coli Genes CA_RS19590 and CA_RS08810 showed significant growth improvement (14.44 and 14.28-fold, respectively, compared to control). This study highlights the potential of machine learning in strain selection and breeding.
期刊介绍:
The Biochemical Engineering Journal aims to promote progress in the crucial chemical engineering aspects of the development of biological processes associated with everything from raw materials preparation to product recovery relevant to industries as diverse as medical/healthcare, industrial biotechnology, and environmental biotechnology.
The Journal welcomes full length original research papers, short communications, and review papers* in the following research fields:
Biocatalysis (enzyme or microbial) and biotransformations, including immobilized biocatalyst preparation and kinetics
Biosensors and Biodevices including biofabrication and novel fuel cell development
Bioseparations including scale-up and protein refolding/renaturation
Environmental Bioengineering including bioconversion, bioremediation, and microbial fuel cells
Bioreactor Systems including characterization, optimization and scale-up
Bioresources and Biorefinery Engineering including biomass conversion, biofuels, bioenergy, and optimization
Industrial Biotechnology including specialty chemicals, platform chemicals and neutraceuticals
Biomaterials and Tissue Engineering including bioartificial organs, cell encapsulation, and controlled release
Cell Culture Engineering (plant, animal or insect cells) including viral vectors, monoclonal antibodies, recombinant proteins, vaccines, and secondary metabolites
Cell Therapies and Stem Cells including pluripotent, mesenchymal and hematopoietic stem cells; immunotherapies; tissue-specific differentiation; and cryopreservation
Metabolic Engineering, Systems and Synthetic Biology including OMICS, bioinformatics, in silico biology, and metabolic flux analysis
Protein Engineering including enzyme engineering and directed evolution.